[Gluster-users] AFR performance killer
gluster at sopca.com
Fri Apr 3 12:52:45 UTC 2009
I've done some benchmarking for various gluster configurations. What I
found out is that write-back(WB) translator in client side - as
suggested in documentation - (almost)always turned out to be a huge
From what I understand WB should "pack" a lot of small writes to fewer
big ones. I cant see that happening in my scenario.
I.e. creating a lot of small files (1kB in size) an self-healing takes
aprox. 10 times longer than without this translator.
Can someone explain this please?
There is also an "option disable-for-first-nbytes" for this translator
which does not seem to be documented.
More information about the Gluster-users